Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    measurements and quantities

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating quantity or measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.86
    wcs
    -0.74
     moderators
    -0.73
     showc
    -0.73
    pmwiki
    -0.69
     traged
    -0.67
    zbollah
    -0.66
     confir
    -0.63
     misunder
    -0.62
     reconc
    -0.62
    POSITIVE LOGITS
    icial
    0.91
     sorts
    0.75
     course
    0.73
     origin
    0.69
    ding
    0.62
     flats
    0.62
     metal
    0.61
     varying
    0.61
     ours
    0.61
     iron
    0.60
    Act Density 0.652%

    No Known Activations